zyacub
/

hugging_face_QA

Question Answering

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

zyacub commited on Aug 12, 2023

Commit

b2c848f

·

1 Parent(s): 47a59c2

update model card README.md

Files changed (1) hide show

README.md +7 -5

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7308
 ## Model description
@@ -42,15 +42,17 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 250  | 1.5837          |
-| 0.9657        | 2.0   | 500  | 1.6448          |
-| 0.9657        | 3.0   | 750  | 1.7308          |
 ### Framework versions

 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the squad dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.1866
 ## Model description
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 5
 ### Training results
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 250  | 2.0354          |
+| 0.3317        | 2.0   | 500  | 2.1035          |
+| 0.3317        | 3.0   | 750  | 2.0138          |
+| 0.313         | 4.0   | 1000 | 2.1020          |
+| 0.313         | 5.0   | 1250 | 2.1866          |
 ### Framework versions